# gpkg-mcp

> Use this tool when you need to automatically extract and manage microservice metadata, scan codebases, and provide insights into service architecture for large-scale projects. It solves problems of service discovery, architecture understanding, and knowledge graph management by seeding Neo4j and exposing query tools for LLM clients. It takes codebases as input and outputs a navigable knowledge graph, ideal for use in complex Moleculer and Go microservice projects.

Canonical page: https://skillsregistry.net/skills/truongtnn404-gpkg-mcp  
JSON: https://api.skillsregistry.net/v1/skills/truongtnn404-gpkg-mcp

## Description

A knowledge graph MCP server for Moleculer and Go microservice projects that scans codebases, extracts service metadata, seeds Neo4j, and exposes tools for LLM clients to query and understand service architecture.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ubw43pjer2)
- **Repository:** <https://github.com/truongtnn404/gpkg-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "truongtnn404-gpkg-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/truongtnn404-gpkg-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/truongtnn404-gpkg-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt